We are building a consumer web application that: - Accepts uploaded PDF documents - Extracts and structures key information - Aggregates multiple documents - Applies rule-based logic to identify patterns - Uses an LLM to generate clear, human-readable explanations - Unlocks deeper analysis via a one-time payment The system is designed to be fully automated, self-serve, and low-touch once deployed. This role is focused on backend development and AI integration only. Frontend design and UX are handled separately. ----- Technical Scope Typical responsibilities include: - PDF text extraction (OCR where required) - Structuring unstructured data using an LLM - Aggregating multiple document records - Exposing clean APIs for a frontend - Generating AI-written explanatory output - Integrating Stripe for one-time payments - Building a simple, reliable, serverless-friendly backend We value clarity and simplicity over complex architecture. ----- Preferred Stack (Flexible) - Node.js or Python - OpenAI API (or equivalent LLM) - PDF parsing / OCR tools - Stripe (one-time payments only) - Serverless hosting (e.g., Vercel-compatible) ---- Deadline Target: Mid-February --- Optional Future Work Improving document parsing accuracy Handling edge-case document formats Automation enhancements AI-driven support workflows